Willi Adrian, Baumann Pascal, Erb Sophie, Gröger Fabian, Zeder Yanick, Lionetti Simone
Department of Computer Science and Information Technology, Lucerne University of Applied Sciences and Arts, Suurstoffi 4, 6343 Rotkreuz, ZG Switzerland.
Surface Measurements, Federal Office of Meteorology and Climatology MeteoSwiss, Chemin de l'Aérologie 1, 1530 Payerne, VD Switzerland.
Aerobiologia (Bologna). 2025;41(2):263-268. doi: 10.1007/s10453-025-09850-4. Epub 2025 Apr 9.
Real-time bioaerosol monitoring is improving the quality of life for people affected by allergies, but it often relies on deep learning models which pose challenges for widespread adoption. These models are typically trained in a supervised fashion and require considerable effort to produce large amounts of annotated data, an effort that must be repeated for new particles, geographical regions, or measurement systems. In this work, we show that self-supervised learning and few-shot learning can be combined to classify holographic images of pollen grains using a large collection of unlabelled data and only a few identified particles per type. We first demonstrate that self-supervision on pictures of unidentified particles from ambient air measurements enhances identification even when labelled data are abundant. Most importantly, it greatly improves few-shot classification when only a handful of labelled images are available. Our findings suggest that real-time bioaerosol monitoring workflows can be substantially optimized, and the effort required to adapt models for different situations considerably reduced.
The online version contains supplementary material available at 10.1007/s10453-025-09850-4.
实时生物气溶胶监测正在改善过敏患者的生活质量，但它通常依赖深度学习模型，这给广泛应用带来了挑战。这些模型通常以监督方式进行训练，需要付出巨大努力来生成大量带注释的数据，对于新的粒子、地理区域或测量系统，必须重复这项工作。在这项研究中，我们表明自监督学习和少样本学习可以结合起来，利用大量未标注数据和每种类型仅几个已识别的粒子对花粉粒的全息图像进行分类。我们首先证明，即使在有大量标注数据的情况下，对来自环境空气测量的未识别粒子图片进行自监督也能增强识别效果。最重要的是，当只有少数几张标注图像可用时，它能极大地改善少样本分类。我们的研究结果表明，实时生物气溶胶监测工作流程可以得到大幅优化，并且为使模型适应不同情况所需的工作量也能大大减少。
在线版本包含可在10.1007/s10453-025-09850-4获取的补充材料。
